home.social

#bioinspiredcomputing — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #bioinspiredcomputing, aggregated by home.social.

  1. "We demonstrate that multilayer ANNs comprised of separate excitatory and inhibitory cell types, and neuronal units with separate dendrite compartments, can be trained to accurately classify images using a fully biology-compatible deep learning algorithm called dendritic target propagation."

    "Cellular and subcellular specialization enables biology-constrained deep learning", Galloni et al. 2026 (Aaron Milstein's lab).
    sciencedirect.com/science/arti

    #neuroscience #BioinspiredComputing #ANNs

  2. Postdoc available in Elisabetta Versace's lab at Queen Mary University of London:

    qmul-jobs.tal.net/vx/mobile-0/

    "This position is funded by a Leverhulme Trust project titled “Generalisation from limited experience: how to solve the problem of induction.” Our goal is to explore parallels between biological and artificial intelligence, with the broader aim of advancing AI through insights from biology."

    #PhDJobs #BioinspiredComputing

  3. Waiting for it, right?

    #ComplexityThoughts issue #19 is coming: amazing new papers,from #ComplexSystems foundations to #BioInspiredComputing #CollectiveBehavior & #UrbanSystems

    Unraveling complexity: building knowledge, one paper at a time!
    Not yet subscribed? It's never too late, and it's 100% free.

    manlius.substack.com/p/complex

    The next #ComplexityThoughts drawn by an AI 👇

  4. In the issue #17 amazing new papers, from #ComplexSystems foundations to #BioInspiredComputing #EvolutionaryDynamics #Ecosystems #CollectiveBehavior & #Neuroscience

    Unraveling complexity: building knowledge, one paper at a time!

    Curious and want to know more?
    Not yet subscribed?
    It's never too late, and it's 100% free.

    🚨 manlius.substack.com/p/complex

    In the figure: a visual preview of the next #ComplexityThoughts as drawn by an AI.

  5. In the figure: the next #ComplexityThoughts drawn by an AI.

    In the issue #16 amazing new papers, from #ComplexSystems foundations to #ClimateChange #Ecosystems and #BioInspiredComputing

    Unraveling complexity: building knowledge, one paper at a time!

    Curious and want to know more
    Not yet subscribed?
    It's never too late, and it's 100% free.

    manlius.substack.com/p/complex

  6. Do we need to hardwire hierarchical connectivity in recurrent neural networks to achieve predictive coding (PC)?

    PC is an emergent consequence of an energy efficiency principle, leading to separate subpopulations of prediction and error units.

    cell.com/patterns/fulltext/S26

    #ComplexSystems #NetworkNeuroscience #BioInspiredComputing #ComputationalBiology

    @neuroscience @networkscience @complexsystems

    @PessoaBrain @WiringtheBrain @kordinglab @ricard_sole @albertcardona @c4computation

  7. “intrinsic stochasticity is probably positively utilized by brains, not only to optimize the signal response but also to induce intelligence itself, and one of the key roles, played by astrocytes in information processing, could be dealing with noises”

    #BioInspiredComputing #ComputationalBiology #MachineLearning @neuroscience

    journals.aps.org/prresearch/ab

  8. The authors propose a simple single-neuron model where the dendrite is implemented as a sequence of thresholded linear units. They manipulate the underlying architecture and investigate the impacts of binary branching constraints and repetition of synaptic inputs on neural computation, finding that models with such manipulations can perform (surprisingly?) well on machine learning tasks.

    #Neuroscience #BioInspiredComputing #MachineLearning @neuroscience

    direct.mit.edu/neco/article-ab

  9. “Neuroevolution enables important capabilities that are typically unavailable to gradient-based approaches, including learning neural network building blocks (for example activation functions), hyperparameters, architectures and even the algorithms for learning themselves [...] This Review looks at several key aspects of modern neuroevolution”

    nature.com/articles/s42256-018

    #Neuroscience #MachinLearning #Neuroevolution #ANN #BioInspiredComputing

  10. New preprint led by @[email protected] about a topic really interesting to me: the bridge between network science and artificial neural networks!

    What happens if we use structured topologies or even real connectomes for some machine learning tasks?

    Thread. 1/

    arxiv.org/abs/2211.00161

    #ComplexSystems #ComplexNetworks #CollectiveBehavior #StatisticalPhysics #BioInspiredComputing Of interest for: #ComputationalBiology #Neuroscience